bart-base-xsum / README.md
morenolq's picture
Add evaluation results on the default config and test split of xsum (#6)
85e42f7
metadata
license: apache-2.0
tags:
  - generated_from_trainer
  - summarization
base_model: facebook/bart-base
model-index:
  - name: bart-base-xsum
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: xsum
          type: xsum
          config: default
          split: test
        metrics:
          - type: rouge
            value: 38.6513
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmIyOTlhYjQ1NTgyMDZiMThjN2NhOTU2N2JiOWRlNmYzMzIyYzQ5NmY1NjdmZWM1ZTBmNDkwYWNlNGJmMjI5ZiIsInZlcnNpb24iOjF9.JW9NwjJOl1i41VQNH12NhOrOgRTTKwm4dirFYxUKDw-QQ9qbNkGe1iut9MAsiS3RVfxzrEM9r_e-craaN06KBA
          - type: rouge
            value: 17.7585
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzcwMTZhODVjMDI4NjBiMDI1ZDNiZjlhZjc2Nzk3ZmQxNmZhYzlkNDUwMWE2NDNlOGE0Y2I4YzdlZWFlYmY1YSIsInZlcnNpb24iOjF9.GAt22--gTCqKOOeUMGtbtkcsjlS6rONCxiU9YXbPz78lwpdmXsLf1d-bo4JNmMLSd8v8n9UMzGPtUYpSKTiDCQ
          - type: rouge
            value: 32.2033
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGJlOWVhY2M4YjNhZmQzMjRhZDk0NGMyN2U3MDI2ZDYxY2I4ZDA5M2RjZjg5MmFlZTgwYTdjNDM0ZjUxN2NmZiIsInZlcnNpb24iOjF9.FZSlI-y-wBrX6SrPjpLAC28oJSCWrRLnFtWnsFQfDZJVOuFFkI4_-R-XSFBrWuC3EzgM2WnuSCmRfzZn3iHWBw
          - type: rouge
            value: 32.2064
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGFlMWIzZmI4OTRjMDZlOTk2MGNlNTQzZDA1MWZkNjhiYWM2ZTFjZGQ0MDYwNGQ0ZjA3Yzk5OTU5ODEwNmFiNCIsInZlcnNpb24iOjF9.K6Ww1AvjfhEAh2msrBhO9SK2TL9szwTJ04S1F_ejLolrHM_YgoeTx38dlAnibKSHKyYEM2DlJt0qmS7nBKKRCA
          - type: loss
            value: 1.822434902191162
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDAyMjBlZTI1MTI4YjRjZmY0ZjliNmNkYTJmY2ZkMjViZGM4MGE1Y2E2MjM0NTNlNDM3MTk1ZGQ0ZWNiZGI3MSIsInZlcnNpb24iOjF9.tA38SX6sMrSATaKdnZbSLxYKDqKIiKseq7yT37gg-6WaU62qw72ij3BZmF-UJWWYCFdNSa-F5FAYkzwL5peGBw
          - type: gen_len
            value: 19.7028
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzU1Njc2YmYxZGM4NjA3ZTMxZmY2YjBmNjhiZmE5YzA5Y2U2NDNjZDM0MWNjZjAwYjYxZWVmNDZjMDc5MGM2YyIsInZlcnNpb24iOjF9.j7cYnDB8LQ_stl35EaHKKJhqavj9mHVroOkzuk88rV8eRWhpksKg-n1FfbXERhxKIUBrQIWszyMUlEvAV5beBQ
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: xsum
          type: xsum
          config: default
          split: validation
        metrics:
          - type: rouge
            value: 38.7415
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjdhZTc4MGUyODM3ZDBjNmVhODRlNDMzNWJmYmNlM2NmZTEwNzc3ZDYwYjllMzc4ZWE4N2FlNWQwNDhjNGZlMiIsInZlcnNpb24iOjF9.a3dZeqsFupDVZOoSrw3FRC7ysZ04930QQKNLLyJkmoSbh6p9J1IVa5Xih3RTmQbYAN2XczTSbpQS7RqpOGE3Dg
          - type: rouge
            value: 17.8295
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTRmN2ZjMDM3NDgwYzVlODcwNmYwZjVlODcxMGE4ZDU5MDQ2ZDdjMjEzZWE2NmNiYzRiZGZmMzkzN2EzZThlYSIsInZlcnNpb24iOjF9.3E8u6Ia8_ri_qcNjshPFEPEyED3cK1dNJr027fdjn0_DjY7PDsnP6pmeNv4YJJSTWTX_itiX69zcdWK5m4WPCQ
          - type: rouge
            value: 32.2861
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzllOGNkYWI4MTdiZDc4MjgxZGUzNWZlYzkyNjlhNTQ3Y2JlMmE0NGZiNGRlMGMxNDkxZWViNjk2OTFmNmJiYyIsInZlcnNpb24iOjF9.cqrqGe65cej66-c3JjQebMx3kiM1nGOVMpN0ZbqnCRFoMdqqCIVG3ZjP-LJY3MptXRqk_sWY_O5kMximu5sgCg
          - type: rouge
            value: 32.2763
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGNkZWQzMzcwY2YyYjE3OWM1ZmJiMTExYmViNTU2NjExZDdmMTQ4OGZkOGZiYjk1OWQ0YTY5YjU5NTI0YjQwNiIsInZlcnNpb24iOjF9.pLFILxKJ33wPSDByZz-IQv_ujRzypMeblgc3C7_3eO5egte0_hTnjl4u-m8KLGYy7mfVXFHZPpvihwlShrARDg
          - type: loss
            value: 1.8132821321487427
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZmRhM2UxMWRhNjk0NmIxODQyNjEyNmEwMzYyYTc3NGZlN2RlNWYyZjE1M2NlNDQyOTM1ZGU2MDQ1OWY1OTYyYyIsInZlcnNpb24iOjF9.ZTCMjc6AwjXjO7mHiVPCSyYX1eAPX5IDbWSckWIQpH7O9qk8Sm4WXST-q26Mtf4WOkn2u26Lf171ATBH5GyCCg
          - type: gen_len
            value: 19.7116
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2JjMzcxZTI0MDQ4ZDk3YTVhYTZjYmRiYmM5MWUwNDM0MjFkOWZiYTNlMWQ1NzA3MDMyNTI5MjY4OGY5ZGYwYiIsInZlcnNpb24iOjF9.JJ41buqEz-r4GSHAAB31_gofuzjEm0fgui9ovJJbJZLTcooGHAbYMBuDAZM8ojwFEu6S2VTR0fJE60OCs278Cg
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: cnn_dailymail
          type: cnn_dailymail
          config: 3.0.0
          split: test
        metrics:
          - type: rouge
            value: 14.9833
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzkzZGVlOGU3NTViZGI4NGRmYTU3MTY1NGYwZjQzODFlODU0YzI2NjBjM2UwMjNlNzUyM2VjZDdjYmYwYjU5MiIsInZlcnNpb24iOjF9.TJxd_x-OeEeb-8wz5Ixiopppw9UbqZuT8cxNZEdUJ_KvUI0IQ1M9t9wh2m877rWkxEStwXrFAOhMK08uY657Aw
          - type: rouge
            value: 3.2788
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDY2NWYyM2ExMjUwODZmOTk2YTk1ZTY4NDFmNDFiNzQ1MTA2YTViZTk4ODIzYzIzMDlkOGE3YjMzOWY0OWZkYSIsInZlcnNpb24iOjF9.wfmE28jxVxpqrpamHdP5-WeKm_LD5NrVeZ1yRjwXo53inVeoUapTQzefMAEmQaTUveL-MLC5rWoQJjiY7QbPBA
          - type: rouge
            value: 11.0507
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTlkZDdiZmY1NmExNWE5ZGIwNzYxMDQ1MmQ3YTFlZjIwZjRjYWRkZGQxYjU5MTdkMWQxOGQ2OGJjNjcxNDU2NyIsInZlcnNpb24iOjF9.xpjIB4PV9UxFzeXhxSxZXE8DPOSRVNlveqOeyzWbhEoQ53TZUpNF5f-E0hXBZhzQCxATwQpIvo52W9eZy8PkDg
          - type: rouge
            value: 13.3138
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzY4YWIwMmZkY2VmM2JhNDc4OTIzMjFlYzJmZGZkY2QxMjJmMTc1Nzg4MWE2YmRlYTYxZDAwMWRkYmE1OTdlYyIsInZlcnNpb24iOjF9.6f6MhSzeXOD3JdKnqW2_3PxLkbUXTBlorNUSww9Xej8jKS8ojaD_Qz-Mi-sbkdslR67szexaC_JHC13K5SlUCQ
          - type: loss
            value: 5.7526116371154785
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDdlODBhMDA5MGE5MjE0MTYyMGU5ZDFjZDYwZWRlYTc5YTY3MWZiYjRkMjc3MzU1YjlhNWVkMDQ0NTk4Mjg2YSIsInZlcnNpb24iOjF9.pNGicJhe2QvE8R_Mn-W1ZIq00ubP6Vc6_-p91DQJ7dHUWpskGTPwEB0wPp7i-XljMRtLW4oreHkihamIXS53Dw
          - type: gen_len
            value: 18.3794
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDQ3YTY2NTFhYTAyMjIzNDhiOWIzYWNmMTliYzEzOTExODI0Zjg5MjQ0MmY3NTJjZDM2OWYwOWQ2YWI4ZmNlYSIsInZlcnNpb24iOjF9.Wx2na6P0y32x2Q2CGiL9G8-8jvNU8pRzlNQrapQniDT8PnXlCw_RlDFn1wpRtv9QZSDizZywp7TxHQ5mTe8wCw

bart-base-xsum

Training: The model has been trained using the script provided in the following repository https://github.com/MorenoLaQuatra/transformers-tasks-templates

This model is a fine-tuned version of facebook/bart-base on xsum dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8051
  • R1: 0.5643
  • R2: 0.3017
  • Rl: 0.5427
  • Rlsum: 0.5427

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss R1 R2 Rl Rlsum
0.8983 1.0 6377 0.8145 0.5443 0.2724 0.5212 0.5211
0.8211 2.0 12754 0.7940 0.5519 0.2831 0.5295 0.5295
0.7701 3.0 19131 0.7839 0.5569 0.2896 0.5347 0.5348
0.7046 4.0 25508 0.7792 0.5615 0.2956 0.5394 0.5393
0.6837 5.0 31885 0.7806 0.5631 0.2993 0.5416 0.5416
0.6412 6.0 38262 0.7816 0.5643 0.301 0.5427 0.5426
0.6113 7.0 44639 0.7881 0.5645 0.3017 0.5428 0.5428
0.5855 8.0 51016 0.7921 0.5651 0.303 0.5433 0.5432
0.5636 9.0 57393 0.7972 0.5649 0.3032 0.5433 0.5433
0.5482 10.0 63770 0.7996 0.565 0.3036 0.5436 0.5435

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.0.0
  • Tokenizers 0.11.6